URSA-1.7B-IBQ512-UDMGRPO-PickScore Model Card

Method Details

Developed by: BAAI
Repository: https://github.com/Yovecent/UDM-GRPO
Paper: UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
Project: https://yovecent.github.io/UDM-GRPO.github.io/

Base Model Details

Developed by: BAAI
Model paper: Uniform Discrete Diffusion with Metric Path for Video Generation
Model family: BAAI-Vision-URSA
Model weight: 🤗URSA-1.7B-IBQ512

Examples

Using the 🤗's Diffusers library to run URSA in a simple and efficient manner.

pip install diffusers transformers accelerate imageio[ffmpeg]
pip install git+ssh://git@github.com/baaivision/URSA.git

Running the pipeline:

import torch
from diffnext.pipelines import URSAPipeline

model_id, height, width, guidance_scale = "Yovecents/URSA-1.7B-IBQ512-UDMGRPO-PickScore", 512, 512, 1.0
model_args = {"torch_dtype": torch.float16, "trust_remote_code": True}
pipe = URSAPipeline.from_pretrained(model_id, **model_args)
pipe = pipe.to(torch.device("cuda"))

prompt = "A cat on a propaganda poster wearing sunglasses"

image = pipe(**locals()).frames[0]
image.save("ursa.jpg")

Uses

Direct Use

The model is intended for research purposes only. Possible research areas and tasks include

Research on generative models.
Applications in educational or creative tools.
Generation of artworks and use in design and other artistic processes.
Probing and understanding the limitations and biases of generative models.
Safe deployment of models which have the potential to generate harmful content.

Excluded uses are described below.

Out-of-Scope Use

The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.

Misuse and Malicious Use

Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:

Mis- and disinformation.
Representations of egregious violence and gore.
Impersonating individuals without their consent.
Sexual content without consent of the people who might see it.
Sharing of copyrighted or licensed material in violation of its terms of use.
Intentionally promoting or propagating discriminatory content or harmful stereotypes.
Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.

Limitations and Bias

Limitations

The autoencoding part of the model is lossy.
The model cannot render complex legible text.
The model does not achieve perfect photorealism.
The fingers, .etc in general may not be generated properly.
The model was trained on a subset of the web datasets LAION-5B and COYO-700M, which contains adult, violent and sexual content.